2023/11/28 by Sajed Jalil, Jalil, Sajed · 2 citations
Computer Science · Decision Sciences · #68T07 #D.2.3 #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #I.2.5 #I.2.7 #Scientific Computing and Data Management #Software Engineering (cs.SE) #Software Engineering Research #Software Engineering Techniques and Practices
paper · pdf · doi:10.48550/arxiv.2311.16429
openalex publication_date 2023/11/28 · openalex created_date 2023/11/30 · openalex updated_date 2026/07/28
The increasing adoption and commercialization of generalized Large Language Models (LLMs) have profoundly impacted various aspects of our daily lives. Initially embraced by the computer science community, the versatility of LLMs has found its way into diverse domains. In particular, the software engineering realm has witnessed the most transformative changes. With LLMs increasingly serving as AI Pair Programming Assistants spurred the development of specialized models aimed at aiding software engineers. Although this new paradigm offers numerous advantages, it also presents critical challenges and open problems. To identify the potential and prevailing obstacles, we systematically reviewed contemporary scholarly publications, emphasizing the perspectives of software developers and usability concerns. Preliminary findings underscore pressing concerns about data privacy, bias, and misinformation. Additionally, we identified several usability challenges, including prompt engineering, increased cognitive demands, and mistrust. Finally, we introduce 12 open problems that we have identified through our survey, covering these various domains.